A reinforcement-learning-based evolutionary algorithm using solution space clustering for multimodal optimization problems
| dc.cclicence | N/A | en |
| dc.contributor.author | Xia, Hai | |
| dc.contributor.author | Li, Changhe | |
| dc.contributor.author | Zeng, Sanyou | |
| dc.contributor.author | Tan, Qingshan | |
| dc.contributor.author | Wang, Junchen | |
| dc.contributor.author | Yang, Shengxiang | |
| dc.date.acceptance | 2021-04 | |
| dc.date.accessioned | 2021-04-20T10:52:29Z | |
| dc.date.available | 2021-04-20T10:52:29Z | |
| dc.date.issued | 2021-06 | |
| dc.description | The file attached to this record is the author's final peer reviewed version. | en |
| dc.description.abstract | In evolutionary algorithms, how to effectively select interactive solutions for generating offspring is a challenging problem. Though many operators are proposed, most of them select interactive solutions (parents) randomly, having no specificity for the features of landscapes in various problems. To address this issue, this paper proposes a reinforcement-learning-based evolutionary algorithm to select solutions within the approximated basin of attraction. In the algorithm, the solution space is partitioned by the k-dimensional tree, and features of subspaces are approximated with respect to two aspects: objective values and uncertainties. Accordingly, two reinforcement learning (RL) systems are constructed to determine where to search: the objective-based RL exploits basins of attraction (clustered subspaces) and the uncertainty-based RL explores subspaces that have been searched comparatively less. Experiments are conducted on widely used benchmark functions, demonstrating that the algorithm outperforms three other popular multimodal optimization algorithms. | en |
| dc.funder | Other external funder (please detail below) | en |
| dc.funder.other | National Natural Science Foundation of China | en |
| dc.identifier.citation | Xia, H., Li, C., Zeng, S., Tan, Q., Wang, J. and Yang, S. (2021) A reinforcement-learning-based evolutionary algorithm using solution space clustering for multimodal optimization problems. Proceedings of the 2021 IEEE Congress on Evolutionary Computation, June 2021. | en |
| dc.identifier.doi | https://doi.org/10.1109/cec45853.2021.9504896 | |
| dc.identifier.uri | https://dora.dmu.ac.uk/handle/2086/20780 | |
| dc.language.iso | en_US | en |
| dc.peerreviewed | Yes | en |
| dc.projectid | 62076226, 61673355 and 61673331 | en |
| dc.publisher | IEEE Press | en |
| dc.researchinstitute | Institute of Artificial Intelligence (IAI) | en |
| dc.subject | Evolutionary algorithm | en |
| dc.subject | reinforcement learning | en |
| dc.subject | landscape approximation | en |
| dc.subject | basin of attraction | en |
| dc.title | A reinforcement-learning-based evolutionary algorithm using solution space clustering for multimodal optimization problems | en |
| dc.type | Conference | en |